model-interpretation
Warn
Audited by Snyk on Aug 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required runtime workflow (
scripts/slice_errors.py/scripts/largest_misses.py) ingests held-out prediction tables from a user-supplied--inputpath and then computes/prints slices and largest-miss rows based on that data, meaning outsider-authored free text can be included via the CSV/JSON/NDJSON fields.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata